NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models (arxiv.org)

13 points by chrsw 7mo ago ↗ HN

0 comments

[ 3.8 ms ] story [ 14.5 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats